Follow-up to BCQuality#22. The previous contract made suggested-code
expected for mechanical findings, but still left too much judgement to
the model. In the synthetic benchmark, BCQ produced omission reasons
for 11 mechanical-looking findings instead of suggestions.
Add explicit must-suggest classes where omission is not allowed when
location points to the affected line/range and the replacement can be
expressed as one contiguous block:
- missing OptionCaption
- missing ToolTip
- formatter-only casing/spacing defects
- Count() existence/repeated-count fixes
- unreachable/dead contiguous blocks
- over-broad permission tokens with an obvious narrower token
- obvious DataClassification additions
- local Label moves when the target range includes both old and new
declaration locations
Update all AL leaf skills and al-code-review to reference these
must-suggest classes.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
BCQ now wins on coverage in the synthetic complex benchmark, but only
2 of 25 rendered comments carried GitHub suggestion blocks while the
AIRHack reviewer emitted suggestions for every finding. Tighten the
DO contract and leaf-skill instructions so suggested-code is no longer
a soft affordance for mechanical fixes.
Changes:
- Add optional findings[].suggested-code-omission-reason to the DO
schema.
- Document suggested-code as expected for small, local, mechanical
findings, with examples (delete unreachable code, Count() > 0 ->
not IsEmpty(), move local Label, add missing ToolTip/OptionCaption,
replace string-concatenated Error, change permission token, add an
obvious else/guard branch).
- Require omission reasons when a mechanical-looking finding omits
suggested-code.
- Update all AL leaf skills and al-code-review guidance with the same
stronger contract.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The original DO contract pinned all agent reasoning to the super-skill:
'Agent findings are emitted only by super-skills... Leaf sub-skills MUST
NOT emit agent findings'. This funnels all agent reasoning across all 6
domains through a single super-skill pass, which is the root structural
cause of the attention dilution we have been chasing in BCAppsBCQuality
PRs #28 and #30:
- T1 standalone run showed al-security-review finds rimd-on-read-only
cleanly when run alone, but emits zero agent findings because the
contract forbids it. So obvious things like case-without-else (no
matching KB article yet) get dropped on the floor.
- The al-code-review self-review pass keeps producing 0-1 agent findings
per PR because it is asked to reason across 6 domains in one pass.
The fix is to move agent reasoning into the leaves, bounded by each
leaf's domain. Each leaf now has both knowledge-backed and agent-finding
permissions within its own scope; the super-skill self-review pass
becomes a smaller, cross-cutting role.
skills/do.md
- Replace the 'only by super-skills' / 'MUST NOT' clause with a
two-tier model: leaf sub-skills MAY emit agent findings strictly
within their declared domain; super-skills MAY emit agent findings
for cross-cutting concerns that span domains.
- Update the encoding rules: leaf agent findings have references:[]
and an agent:-prefixed id, no from-sub-skill (the leaf's own report
carries the finding under its own skill.id). Super-skills set
from-sub-skill='agent' for their own self-review findings; when
rolling up leaf agent findings, they set from-sub-skill=<leaf-id>.
- Clarify that 'MUST validate against knowledge' applies to super-
skill self-review candidates only - leaves already validated within
their domain when they decided to emit.
microsoft/skills/review/al-{security,performance,privacy,style,upgrade,
ui}-review.md
- New paragraph after the confidence rules instructing each leaf to
surface domain-specific agent findings when no knowledge file
covers a defect the agent recognises from general AL knowledge.
- Bound the scope: 'The scope is strictly <domain>; defects outside
this domain belong to other leaves and MUST NOT be emitted here.'
- Same validation requirement: check the worklist for a matching
knowledge file first; if one exists, upgrade to a knowledge-backed
finding instead.
microsoft/skills/review/al-code-review.md
- Rewrite the 'Agent self-review pass' subsection. The pass is now
explicitly for cross-cutting concerns that no single leaf could
have surfaced because they span multiple domains. Domain-specific
reasoning belongs in the leaves, not duplicated here.
- Update the rollup behavior to acknowledge leaf-emitted agent
findings: they are rolled up like any other sub-skill finding, with
from-sub-skill set to the leaf id, and are not re-validated by the
super-skill (the leaf already validated within its own domain).
- Drop the 'Leaf sub-skills MUST NOT emit agent findings' line.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Drop the specific pattern checklist (architecture-level smells, error-
handling gaps, magic constants, privacy/telemetry surface, resource
lifecycle - with concrete code patterns under each). It baked case-
study findings into the skill contract and aged badly. Replace with a
domain-level framing: walk by the domains the sub-skills already cover
(performance, security, privacy, style, upgrade, UI) plus the cross-
cutting concerns (architecture, error handling, resource lifecycle).
The domains are anchors for completeness, not a script.
The structural rule - do an explicit self-review pass after the leaves
- is what carries the value. The content of the pass belongs in the
agent's general AL judgement and in the knowledge layer.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Driven by a parity comparison between BCAppsBCQuality PR #27 and
BCAppsCampAIRHack PR #162 on byte-identical content:
| | BCQuality | AIRHack |
|--|--|--|
| Total findings | 6 | 10 |
| Performance | 0 | 4 |
| Security | 0 | 5 |
Standalone runs of al-security-review and al-performance-review against
the SAME diff produced the expected matches (rimd-on-read-only via
inherent-permissions-minimal-grant; redundant-Get via
avoid-redundant-get-when-record-already-loaded). The miss in the live
run is therefore not a knowledge-coverage gap and not a worklist
filtering issue. It is attention dilution inside the al-code-review
super-skill, which the model collapses into one rolled-up generation
pass on real-size PRs.
Changes:
microsoft/skills/review/al-code-review.md
- New 'Execution discipline (mandatory)' subsection in the Action step
that explicitly forbids collapsing leaves into one shared reasoning
pass and requires each sub-skill to walk its Source -> Relevance ->
Worklist -> Action steps as its own iteration before the next leaf
starts.
- Self-review pass is now described as the final, mandatory iteration
with a concrete candidate-category checklist (architecture-level
smells, error-handling gaps, magic constants, privacy/telemetry,
resource lifecycle). Returning zero agent findings on a real-size
diff is explicitly defined as a defect.
microsoft/skills/review/al-{security,performance,privacy,style,
upgrade,ui}-review.md
- Each leaf skill now states that when an unambiguous .good.al
companion exists, findings[].suggested-code should carry the
literal replacement for the source lines. Closes the
one-click-suggestion gap created when BCQ#19 only updated
al-code-review.
microsoft/knowledge/security/case-must-handle-unknown-enum-values.{md,
bad.al,
good.al}
- New article: case over a security-sensitive enum (Authentication
Type, Authorization Mode, Identity Provider, Permission Scope,
Encryption Algorithm) MUST have an else arm. Without it, an unknown
enum value silently falls through and the security context never
initialises. The bad sample is lifted from the SharePoint Graph
helper that triggered the parity finding.
microsoft/knowledge/performance/instream-length-unreliable-for-bc-
streams.{md,bad,good}
- New article: InStream.Length returns 0 / partial for HTTP-response
streams and some file-API streams, breaking size-threshold branching
in upload code. Bad sample is the simple-vs-chunked Graph upload
pattern; good sample materialises into a Temp Blob first.
Companion change: microsoft/BCAppsBCQuality#28 extends the
orchestrator's bootstrap prompt with the same per-iteration execution
discipline and adds a CI warning when a >5-file PR returns zero agent
findings (regression signal).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Adds the contract field, skill instructions, and two knowledge articles
that BCAppsBCQuality's PR-review agent needs to match (and exceed) the
coverage of the embedded review agent in BCAppsCampAIRHack:
skills/do.md
- New optional findings[].suggested-code field. Documents what it MUST
contain (a literal line-replacement payload) and when to emit it.
microsoft/skills/review/al-code-review.md
- Instructs both the agent self-review pass and rolled-up sub-skill
findings to populate suggested-code when the fix is mechanical.
- Lists examples (dead code removal, Count > 0 -> IsEmpty, object-scope
Label) that map to issues observed in the parity comparison.
microsoft/knowledge/style/telemetry-event-id-stable-unique.{md,bad.al,good.al}
- New knowledge article: telemetry event IDs must be stable, unique,
and non-placeholder. Closes a gap surfaced by the parity comparison.
microsoft/knowledge/style/labels-declared-at-object-scope.{md,bad.al,good.al}
- New knowledge article: Labels must live in the object-level var
block, not in procedure-local var blocks. Closes the second gap.
microsoft/knowledge/privacy/no-pii-in-telemetry-message-string.md
- Adds an explicit note that changing DataClassification alone does not
make embedding PII into the message string acceptable, plus links to
the two adjacent privacy articles. Resolves the privacy advice the
parity comparison flagged as ambiguous.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Let super-skills surface findings the agent identifies on its own,
clearly tagged so consumers can render them differently from
knowledge-backed ones.
- skills/do.md: permit references:[] when from-sub-skill='agent';
define the agent-finding encoding (id 'agent:<slug>', confidence
capped at medium, self-contained message); restrict agent findings
to super-skills only.
- microsoft/skills/review/al-code-review.md: add a self-review pass
to Action that validates agent-identified candidates against
BCQuality (cite if matched, suppress if contradicted, surface as
agent finding otherwise). Add example finding.
- agent-consumption.md, README.md: describe the additive model and
the from-sub-skill: 'agent' marker so consumer orchestrators know
to render unbacked findings.
Strictly additive: existing knowledge-backed flow is unchanged and
backward compatible.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The knowledge corpus now covers performance, security, privacy, upgrade,
style, and UI. Previously only two leaf reviewer skills existed
(al-performance-review, al-security-review), so four of the six domains
had knowledge with no skill sourcing from them. A community reader
landing in privacy/, upgrade/, style/, or ui/ would see articles with
no apparent consumer.
Three changes:
1. Move existing review skills into `microsoft/skills/review/`. The
`review/` subfolder groups all review-kind skills together and leaves
room for future non-review action skills at the `microsoft/skills/`
level. Updates references in README.md, agent-consumption.md, and
skills/entry.md to the new paths.
2. Add four new leaf reviewer skills — al-privacy-review,
al-upgrade-review, al-style-review, al-ui-review — each following
the same DO template as al-performance-review/al-security-review but
sourcing from the corresponding knowledge domain. al-upgrade-review
and al-ui-review return `not-applicable` when the diff contains no
upgrade surface or no page files, respectively.
3. Update al-code-review to compose all six leaf skills and retarget
the dangling references in every populated JSON example
(`use-setloadfields.md`, `no-plaintext-secrets-in-telemetry.md`,
`avoid-implicit-commit.md` — none of which exist in the corpus) to
real knowledge files: `call-setloadfields-before-filters.md`,
`use-secrettext-for-credentials.md`, `never-hardcode-secrets-in-al.md`.
Validator passes with 0 errors / 0 warnings.
Most of the corpus — FindSet/SetLoadFields/CalcFields patterns, permission
sets, SingleInstance codeunits, DataClassification, IsolatedStorage,
transaction scope, SecretText — describes BC platform behaviour that is
identical across supported versions. The seed [26..28] range on every
file implied a version-specificity the content does not actually have,
and there was no way to express "applies to every version" in the
schema the way [w1] and [all] already do for countries and
application-area.
Extend the v1 schema with a universal sentinel for bc-version, parallel
to the sentinels already defined for the other dimensions:
bc-version: [all] # applies to every BC version
[all] is mutually exclusive with explicit versions. Range shorthand
([26..28]) and explicit lists ([26, 27, 28]) continue to work for files
genuinely tied to a version-gated API or deprecation.
Update read.md (field definition, matching semantics, partial-context
rule), write.md (default to [all], use ranges only with a concrete
reason), README.md (frontmatter example), and the CI validator. All
forty existing knowledge files and the three action skills convert to
[all]; none of the current content is version-gated. Validator passes.
- Introduced unit tests for the bc-domain-context implementation, covering various scenarios including filtering by application area, technology mismatches, layer precedence, and conditional applicability.
- Added knowledge files related to finance, including topics such as Chart of Accounts, Codeunit 12, Dimension Management, and VAT on prepayment chains, among others.
- Each knowledge file includes structured metadata and best practices to enhance the domain knowledge available for Business Central tasks.
DO contract (skills/do.md)
- New 'sub-skills' optional frontmatter field on action skills: when
present and non-empty, the skill is a super-skill that composes
other action skills.
- New 'Composition (super-skills)' section covering section
interpretation, outcome rollup, summary aggregation, and suppression
scope.
- Output schema gains three optional fields: 'from-sub-skill' on each
finding, top-level 'sub-results[]' carrying nested findings-reports,
and top-level 'skipped-sub-skills[]'.
- Super-skills MUST NOT filter sub-skills by task content; leaves own
task-level applicability and signal via outcome.
- Findings from a failed sub-skill MUST NOT flow into the parent's
findings[] or counts, consistent with DO's rule that consumers
ignore a failed skill's findings. Reports are still preserved in
sub-results[] for traceability.
- Rolled-up non-citation finding ids MUST be prefixed with the sub-
skill id to prevent collisions across sub-skills. Citation-based
ids are already unique via repo path and are not rewritten.
- Outcome rollup rules updated: 'partial' covers S = {partial},
{partial, partial}, and {partial, failed}. Empty worklist rolls up
to 'not-applicable' with outcome-reason.
- Nested super-skills are not permitted in v1.
Reference skills (microsoft/skills/)
- al-code-review.md rewritten as the canonical super-skill: lists
al-performance-review and al-security-review as sub-skills, orch-
estrates invocation, aggregates output, and includes a worked
rolled-up JSON example plus the empty-corpus rollup.
- al-performance-review.md added as a leaf reference skill for the
performance knowledge domain.
- al-security-review.md added as a leaf reference skill for the
security knowledge domain.
- Both leaves retain the leaf-level rules validated in the prior
pass: partial-context message requirement, worklist-scoped
suppression, application-area semantics, and the platform-guarantee
threshold for blocker severity.
README updated to describe leaf vs super-skill and link all three
reference skills.
Two rubber-duck passes tightened the contract and caught schema
violations in the worked examples before commit.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- microsoft/skills/al-code-review.md: full action skill reviewing AL
source changes. Exercises every part of the DO contract:
- frontmatter with all required action-skill fields and the four
optional knowledge filters
- all five required sections (Source, Relevance, Worklist, Action,
Output) in order
- applicability-based filtering with READ's partial-context rule,
including the requirement to name unknown dimensions in the
finding message
- conflict resolution and suppression scoped to worklist candidates
- full outcome taxonomy handled (completed, no-knowledge,
not-applicable, partial, failed), including the current empty-
corpus state
- worked JSON output example showing structured references,
per-finding confidence, and a suppression entry
- README.md: link the skill as the canonical reference so skill
authors have a starting point.
Two rubber-duck passes caught and fixed contract precision issues
before commit: location.line/range consistency, partial-context
message requirement, over-broad suppression scope, application-area
matching semantics, and the blocker severity threshold.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
